Karthik, K.Kamath S․, S.2026-02-042022International Journal of Biomedical Engineering and Technology, 2022, 40, 2, pp. 168-18317526418https://doi.org/10.1504/IJBET.2022.125575https://idr.nitk.ac.in/handle/123456789/22749Classification and retrieval of medical images (MedIR) are emerging applications of computer vision for enabling intelligent medical diagnostics. Medical images are multi-dimensional and require specialised processing for the extraction of features from their manifold underlying content. Existing models often fail to consider the inherent characteristics of data and have thus often fallen short when applied to medical images. In this paper, we present a MedIR approach based on the bag of visual words (BoVW) model for content-based medical image retrieval. When it comes to any medical approach models, an imbalance in the dataset is one of the issues. Hence the perspective is also considering a balanced set of categories from an imbalanced dataset. The proposed work on BoVW model extracts features from each image are used to train supervised machine learning classifier for X-ray medical image classification and retrieval. During the experimental validation, the proposed model performed well with the classification accuracy of 89.73% and a good retrieval result using our filter-based approach. © © 2022 Inderscience Enterprises Ltd.DiagnosisMedical imagingSupervised learningBag-of-visual-wordsContent based medical image retrievalContent-basedEmerging applicationsImages classificationSpace modelsSwarm optimizationVisual spaceVisual space modelingWord modelingImage classificationabdominal radiographyankle radiographyArticlebag of visual words modelcomparative studycomputer visiondiagnostic accuracydiagnostic imagingfeature extractionfoot radiographyhand radiographyhistogramimage registrationimage retrievalk means clusteringknee radiographymodelparticle swarm optimizationscale invariant feature transformshoulder radiographysupervised machine learningthorax radiographyvalidation studyX ray