A mobile station MS has a transducer or other interface to receive a media sample, a processor to extract features from a digital version of the media sample, a transmitter to transmit those extracted features, and preferably a buffer so feature extraction can begin on a portion of music received prior to a user input to identify the media sample. The features describe the content of the digital version of the media file. A server receives the extracted features from the MS, extracts additional features which may be higher order features extracted from the MS-extracted features and/or lower order features extracted from a segment of the digital media sample sent from the MS. The server uses all extracted features to search a database and identify the underlying file from which the media sample is taken. A single user entry at the MS initiates the feature extraction, link setup, and transmittal of features. A further entry purchases a copy of the entire media file that is downloaded to the MS.