Mobile Visual Search (MVS) is an emerging area of research given the explosion of smart and computationally powerful mobile devices. Typically, MVS involves the computation of local image features which are then used within a matching process. Such applications pose certain unique challenges due to computation, power and bandwidth constraints of the mobile device. This paper examines the trade-off between two general frameworks for implementing MVS: 1. sending compressed images and performing feature extraction and matching on a server; and 2. performing feature extraction on the mobile device and sending these to a server for matching. A number of local image feature algorithms are studied using various image compression schemes from the point view of matching accuracy and processing time. Results show that the matching accuracy of sending compressed images is comparable to sending compact image features when using a high quality image coder, in this case JPEG2000 and HDPhoto.