This paper describes a query language and a complex event processing (CEP) system over multiple continuous XML data streams. First, multiple stream processing is formulated in algebraic expressions for stream filtering, union, activation, decomposition and partition. Next, a query language, called QLMXS, over XML streams is defined on all functions of the algebraic models in an SQL-like form. Finally, a CEP system is proposed for processing QLMXS queries. The performance of the system is dominated by parsing XML documents and finding specific sequences of events. The former is resolved by adopting VTD parser, which is a modern XML parser and faster than the traditional technologies of DOM, SAX and StAX. The latter is achieved by a finite state automaton (FSA) that determines the acceptance of the event sequences represented in QLMXS queries. Experimental results demonstrate that the performance of the proposed QLMXS system becomes 1.7 times faster than the previous implementation which used the StAX parser and the visibly pushdown automaton (VPA) as cores of the analytical engines.