Content-based image retrieval on CT colonography using rotation and scale invariant features and bag-of-words model

We present a content-based image retrieval (CBIR) paradigm to enhance computed tomographic colonography computer-aided detection (CTCCAD). Our method uses scale-invariant feature transform (SIFT) features in conjunction with the bag-of-words model to describe and differentiate 3D images of CTCCAD detections. We evaluate the performance of our system using both digital colon phantoms and detections form CTCCAD. Our method shows promise in distinguishing common structures found within the colon.