Manual processing of recorded EEG data for characteristics like epileptic spikes is very time consuming since the recording of EEG for a longer duration producing enormous amount of data. Therefore, automated systems are required to speed up the processing. In the current work, a classification method has been proposed for detecting the epileptic spikes in the recorded EEG data by using Linear Discriminant Analysis (LDA) and has been named LDASpike. The prerecorded EEG data files were used as input to LDASpike and the output produced was the total number of spikes present in each EEG file. The proposed method results on an average sensitivity 100% and selectivity 95.38%, when the training and testing data were same. However, with four fold cross-validation applied in this work, the sensitivity and selectivity were achieved as 98.45% and 96.06%, respectively, on an average. Though a little time initially is spent to train the system but the result produced by the system is very promising and can be compared with the existing standard methods. This system can also works with the real time recording and processing for a clinical setup.