This paper addresses the problem of automated prosthesis modelling and manufacturing, whose machining parameters are based on images extracted from different medical databases. The specific case of 3D surface restoration of a defective skull was used as study case. A method based on adjusted ellipses on skull bone curvature performs the symbolic representation of searching parameters. The superellipse concept permits to define geometric parameters to fit an ellipse on each Computed Tomography slice. Those ellipse descriptors can be used as a template for the retrieval of similar images from databases whose parameters match the sampled image. The similarity is measured according to the best fitness values through an optimization algorithm. The slices found by similarity are retrieved from all databases in order to build the 3D model. Experiments show that the proposed method is a promising technique for content based image retrieval.