The current interest amongst researchers in CAD field is the retrieval of components similar to a predefined geometry from a database of CAD models. The design efforts made earlier can be used to reduce the modelling time. After critically reviewing the available literature in this field, the authors propose a new approach to upload and retrieve information on CAD models that will result in reduced computational effort. To discriminate the shape information, principles of solid analytical geometry were used to incorporate sensitivity in differentiating concave and convex features. Shape descriptors are used for similar shape retrieval and benchmarking was done against various standard measures and these findings are reported in this paper. Copyright © 2011 Inderscience Enterprises Ltd.