Abstract: Content based image retrieval is a technique which uses visual contents like shape, color and texture to retrieve images from large scale image databases. In content based image retrieval shape is one of the primitive feature for image retrieval. Many images are classified and detected based on shape description. In this paper we present the methods for retrieving images from the large database which consist of engineering objects or models. The proposed work uses the shape information from an image along with 3D information. The 3D information can be obtained by obtaining depth map, for this a linear approximation procedure that can capture the depth information using the idea of shape from shading has been used. Retrieval of objects is done using a similarity measure that combines shape and the depth information.